At what, 10 tokens per hour? These disk swapping methods all have the same drawbacks - kill your drive early, and slow as hell.

▲

kennywinker 5 hours ago | parent | next [-]

It says very prominently in the post: 4.5-5t/s for 80b on an M5

▲

throwawayffffas 40 minutes ago | parent | prev | next [-]

Am I the only one that has no flash lifetime anxiety? I still have drives from more than a decade ago that keep on chugging fine.

I remember the time spinning rust was the only option and reliable they weren't. In 30 years of computing I have had more than ten hdds and zero ssds die.

▲

wat10000 5 hours ago | parent | prev [-]

Isn’t it only writes that kill drives?

▲

petu 4 hours ago | parent | next [-]

There's read disturb on SSDs, enough reads will eventually force controller to rewrite the cell and it's neighbours.

Practically if you're not streaming weights 24/7 from a full SSD, then it shouldn't be a problem.

	▲	zozbot234 an hour ago \| parent [-]
		Read disturb ought to be quite rare, especially on a fresh drive that was written only once or a handful of times (WORM-like usage). Practically, it's not likely to be an issue even with very heavy read workloads.

▲

sudo_cowsay 5 hours ago | parent | prev | next [-]

Yeah, that's why most of these comments seem weird to me.

▲

Alpha3031 5 hours ago | parent | prev [-]

Yes for NAND, and I suppose nobody is using mechanical hard drives for this.